© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69923
    Prev
    Next
    INDEX
    Explanations

    Queen followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to occurrences of “Queen” used as part of a proper name or title (e.g. Queen Mary, Queen’s University, Queen Victoria).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilesh
    -0.93
     üblichen
    -0.84
     Räume
    -0.84
     antworte
    -0.82
     Eigentü
    -0.81
     betreffenden
    -0.81
     verheir
    -0.81
    ısından
    -0.80
     bisherigen
    -0.79
     景点
    -0.78
    POSITIVE LOGITS
    Queen
    1.46
     Queen
    1.40
    👑
    1.37
    👸
    1.15
     QUEEN
    1.15
     bee
    1.14
     queen
    1.05
     Lati
    0.98
    stown
    0.97
    Bee
    0.96
    Activations Density 0.011%

    No Known Activations